Single-trial Event-related Potentials Denoising based on Collaborative Filtering in Transform Domain
Yue Huang, Xinghao Ding · 2014
Single-trial event-related potentials (ERPs) denoising is still a challenge in both neuroscience research and signal processing. Single-trial ERPs denoising based on ERP image processing has received more attentions. Due to the high self similarity of the ERP images, collaborative filtering considers non-local and enforcing the sparsity in the transform domain simultaneously is presented to remove the strong back ground noise of ERP images. The work generated ERP image from the trials, and then the collaborative filtering, including image patch grouping, shrinkage in 3D transform domain, and aggregation is applied to remove the background noise from the ERP images. The results have been evaluated with both simulated data and real ERPs. The comparison has demonstrated that the collaborative filtering outperforms than popular method wavelet.